June 29, 2022

Growing storage densities require aggressive software management to maintain performance

Denser QLC NAND offers a limited number of write cycles compared to TLC and MLC NAND, while SMR drives offer increased densities for platter hard drives.

One of the recurring problems in IT is the need for more data storage. The amount of business and personal data generated is huge and continues to grow – cloud services company Domo estimates that for every person on earth, 1.7MB of data will be created every second by 2020. This, in turn, creates demand for more storage, and more dense Storage: If a 4TB and 8TB drive both consume 9W of power in operation, the cost savings for power only discs a demand for denser storage. It also says nothing about the cost of the equipment, as well as the rack space and real estate required to deploy these systems, a major issue as IT continues to move closer to the edge.

These increased densities come at a cost: for Flash storage, increased densities result in decreased write endurance. While block reads are essentially unlimited, block write endurance decreases as density increases – 3D MLC NAND is rated for 6,000 to 40,000 cycles, 3D TLC NAND for 1,000 to 3,000 cycles and 3D QLC NAND (four bits) for 100 to 1000 cycles.

Comparatively, QLC NAND SSDs are inexpensive from a cost per GB perspective, although the relative lack of write endurance makes them a poor solution for a variety of applications.

“When people understand QLC’s underlying technology and drive endurance, it’s an eye opener,” said Matt Hallberg, senior product marketing director at Toshiba Memory America. “There is a large semiconductor company that has a QLC drive, and the endurance is about 0.2 drive writes per day (DWPD). the reader’s life. ”

Hallberg is also quick to dismiss QLC’s perceived cost advantage. “The cost savings that people think are there… everyone expects QLC to have a 40% price difference. You actually go from three layers to four layers. It’s not a 40% change… it’s really 20 – 25%. There are additional things you need to do with QLC that actually increase your costs depending on how your QLC is implemented. ”

SEE: The Five Best On-Premises Cloud Storage Options (Free PDF) (TechRepublic)

Performance management for QLC can be done in a moderately transparent fashion, and there are a number of approaches to doing this, according to Joseph Unsworth, vice president of research at Gartner, who said, “QLC technology is a It is imperative for NAND providers to sustainably reduce costs in the future, “and that enterprise storage environments” will increasingly adopt the technology. ”

The first of these is that SSD manufacturers are adopting “advanced techniques for managing flash … performance and preserving write endurance.”

Storage analysis can be used to monitor disk health and predict impending disk failure.

Another approach is Intel’s H10 SSD, which combines their Optane (3D XPoint) storage class memory (SCM) with QLC NAND on a single M.2 drive. This design essentially makes Optane memory a hot cache. Indeed, this model of SCM + QLC is akin to the hybrid drives of yesteryear that combined NAND Flash with traditional platter drives, according to Tim Stammers, senior analyst at 451 Research.

The Difficulties of Magnetic Shingle Recording

For the traditional disk drive market, Magnetic Shingle Recording (SMR) is used to a large extent by all three drive manufacturers. SMR readers are slower than conventional readers and are not precisely instant replacements, whereas there are plug-and-play implementations, known as “reader-driven SMRs,” Western Digital warns against this in a blog post: “The background ‘maintenance’ tasks that the drive must perform results in highly unpredictable performance, unsuitable for business workloads.”

Western Digital touts the Host Managed SMR, in which the host system is responsible for managing data flow, zone management, and I / O operations. This management of hosts necessarily requires support up the stack, and these disks would not be easily used for desktop systems and would require slightly higher processing capacities of storage devices to handle these tasks.

Western Digital is candid about these challenges, noting that the additional capacity (around 16%) granted by SMR “is not free”, noting that “the use of this capacity requires a commitment on the part of the customer to invest in software development in both the file system and the underlying applications, ”adding that“ this investment can pay dividends in the long run, as an SMR drive offers a lower cost per TB and a higher total cost of ownership (TCO) if we consider the investment and operating costs of the data center. ”

“[Cloud vendors] will do the work on the host side to support SMR capability, but most of the other use cases are definitely not ready, they won’t be designed for SMR, ”said Scott Wright, Director of Product Marketing at Toshiba.

“Complete Confidence” for Dual Actuator Drives

As densities increase on traditional platter drives, the ratio (I / O operations per second) per TB continues to decline. Segate and Western Digital have publicly discussed their intention to move towards dual-actuator hard drives.

This isn’t the first time this has been attempted, with an attempt in the mid-90s of Conner Peripherals’ “Chinook” niche drives, known to fail prematurely due to increased vibration causing head collisions. . However, modern implementations seem to have “complete confidence” in the industry, according to John Monroe, vice president of research at Gartner, who notes that “necessity is the mother of invention, and at 16TB and above. , multi-actuators will be a necessity. ”

Also look

Close up of an open open computer hard drive.  Data security concept.

Image: Getty Images / iStockphoto